INDEX

Explanations

questions and answers related to creating and inspiration for art or writing

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Answers to questions

np_acts-logits-general · gemini-2.0-flash

Washington Wide

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 виправивши

-0.98

 entanto

-0.84

 Trotzdem

-0.84

 therefore

-0.79

μως

-0.78

Поэтому

-0.74

จึง

-0.69

それでも

-0.69

همچنین

-0.68

 zudem

-0.68

POSITIVE LOGITS

Depends

1.17

 Depends

1.16

 depends

1.09

Honestly

1.01

 honestly

0.98

 Honestly

0.96

うーん

0.91

 dipende

0.91

 firstly

0.89

 definitely

0.89

Activations Density 0.183%

questions and answers related to creating and inspiration for art or writing

Answers to questions

Washington Wide

No Comments

No Known Activations